Problem Solving using Recurrent Neural Network based on the Effects of Gestures

Sanghun Bang, Charles Tijus

2018

Abstract

Models of puzzle problem solving, such as Tower of Hanoi, are based on moves analysis. In a grounded and embodied based approach of cognition, we thought that gestures made to take the discs to one place and place them in another place could be beneficial to the learning process, as well as to the modeling and simulation. Gestures comprise moves, but in addition they are also prerequisites of moves when the free hand goes in one location to take a disc. Our hypothesis is that we can model the solving of the Tower of Hanoi through observing the actions of the hand with and without objects. We collected sequential data of moves and gestures of participants solving the Tower of Hanoi with four dicks and, then, train a Recurrent Neural Network model of Tower of Hanoi based on these data in order to find the shortest solution path. In this paper, we propose an approach for change of state sequences training, which combines Recurrent Neural Network and Reinforcement Learning methods.

Paper Citation

in Harvard Style

Bang S. and Tijus C. (2018). Problem Solving using Recurrent Neural Network based on the Effects of Gestures. In Proceedings of the 10th International Joint Conference on Computational Intelligence (IJCCI 2018) - Volume 1: IJCCI; ISBN 978-989-758-327-8, SciTePress, pages 211-216. DOI: 10.5220/0006931802110216

in Bibtex Style

@conference{ijcci18,
author={Sanghun Bang and Charles Tijus},
title={Problem Solving using Recurrent Neural Network based on the Effects of Gestures},
booktitle={Proceedings of the 10th International Joint Conference on Computational Intelligence (IJCCI 2018) - Volume 1: IJCCI},
year={2018},
pages={211-216},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006931802110216},
isbn={978-989-758-327-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Joint Conference on Computational Intelligence (IJCCI 2018) - Volume 1: IJCCI
TI - Problem Solving using Recurrent Neural Network based on the Effects of Gestures
SN - 978-989-758-327-8
AU - Bang S.
AU - Tijus C.
PY - 2018
SP - 211
EP - 216
DO - 10.5220/0006931802110216
PB - SciTePress